bug-ops

Zeph configuration reference for LLM providers, memory, tools, channels, and features. Use when the user asks about setup, configuration, environment variables, TOML settings, or how to enable specific features like Telegram, Qdrant, A2A, MCP, Candle, or orchestrator. Keywords: config, setup, install, configure, toml, environment, provider, feature, enable.

Switch to ultra-compressed, telegraphic output. Use when the user asks for terse, brief, minimal, "caveman", or no-fluff answers; wants responses with articles and filler words dropped; or requests maximally short fragments. Keeps code blocks, file paths, commands, and identifiers intact and verbatim.

Cross-platform OS automation — send desktop notifications, read and write the clipboard, take screenshots, open files and URLs in default apps, launch and manage applications, control system volume, check WiFi status, create scheduled tasks and cron jobs, and manage display brightness. Use when the user asks to send a notification, copy to clipboard, take a screenshot, open a file or URL, launch an app, adjust volume, check WiFi, schedule a task, or control OS UI and system settings on macOS, Windows, or Linux. Do not use for running arbitrary shell commands or scripts — use the shell tool instead.

Monitor, manage, and control system processes. Use when the user asks to list running processes, find a process by name or PID, kill or terminate processes, manage background jobs, check resource usage, set resource limits, manage system services with systemctl or launchctl, or troubleshoot CPU and RAM usage with ps, top, htop, kill, pgrep, and related tools.

Handoff protocol for the Rust multi-agent development team (rust-architect, rust-developer, rust-testing-engineer, rust-performance-engineer, rust-security-maintenance, rust-code-reviewer, rust-cicd-devops, rust-debugger, rust-critic). Use only when orchestrating subagents via structured YAML files in .local/handoff/. Not for general agent interactions or memory updates.

Send HTTP API requests using curl. Use when the user asks to call an API, fetch data from a URL, send POST/PUT/PATCH/DELETE requests, work with REST or GraphQL endpoints, upload files, authenticate with Bearer tokens or API keys, debug HTTP responses, or interact with any web service via HTTP.

Browser automation via Playwright MCP — navigate pages, click elements, fill forms, take screenshots, extract text, manage tabs, and run JavaScript in the browser. Use when the user asks to open a website, interact with a web page, scrape dynamic content, fill out forms, take a page screenshot, test a web application, or automate browser workflows. Requires a Playwright MCP server configured in [[mcp.servers]].

LSP-based code analysis via mcpls MCP server. Use for compiler-accurate type inspection, go-to-definition, find-all-references, diagnostics, call hierarchy, workspace symbol search, code actions, rename refactoring, and document formatting. Provides real compiler errors — not guesses. Keywords: LSP, language server, type, definition, references, diagnostics, hover, symbol, call hierarchy, rename, refactor, code actions, rust-analyzer, pyright, gopls, clangd.

Orchestrate a continuous improvement cycle: spawn rust-live-tester for live testing, rust-researcher for dependency monitoring and research, rust-arch-analyst for code quality and architecture review, and rust-security-analyst for vulnerability scanning. Aggregates findings and produces a cycle summary.

Initialize a Rust project for the rust-agents plugin: scaffold .local/ working directories, .claude/rules/ project rules, testing knowledge base, and .gitignore. Run once when starting a new project.

Vulnerability and security-hardening audit protocol for Rust projects. Activates expert knowledge across dependency advisories, unsafe code, secret exposure, injection and input validation, cryptography misuse, authentication and authorization, panic-based denial of service, and supply-chain trust. Called by rust-security-analyst at startup via Skill(...). When invoked directly as /security-audit [focus], the current session runs the audit without spawning subagents.

Reference for stable Rust APIs added in versions 1.89 through 1.97 (August 2025 - July 2026). Use this skill whenever writing, reviewing, or refactoring Rust code — especially when you notice patterns that were verbose before newer APIs existed, when MSRV allows it, or when the user mentions modernizing Rust code, upgrading MSRV, or using "the latest Rust features". Also trigger when reviewing Rust code for improvements, migrations, or when a user asks "can this be simpler in modern Rust?" Proactively suggest newer APIs when you see patterns like manual UTF-8 truncation, path extension manipulation, advisory file locking via external crates, ignoring `retain` removal results, verbose `try_into().unwrap()` for fixed arrays, `compare_exchange` loops for atomic update, `cfg_if` crate usage, matching `0`/`1` to `bool`, `assert!(matches!(...))` in tests, or hand-rolled bit-manipulation idioms like `1 << (BITS - 1 - x.leading_zeros())`.

Debug Rust issues using a multi-agent investigation team. Workflow: debugger + live-tester (conditional) investigate root cause in parallel → security review always, architect and perf reviews conditionally → code reviewer consolidates findings → results presented to user. Requires rust-agents plugin and CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.

Orchestrate Rust development using agent teams with peer-to-peer communication. Use when: 'create rust team', 'start team development', 'launch agent team', 'team workflow', 'collaborative development'. Requires rust-agents plugin and CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.

Architecture and code quality audit protocol for Rust projects. Activates expert knowledge across type safety, modularity, testability, readability, DRY, and async concurrency. Called by rust-arch-analyst at startup via Skill(...). When invoked directly as /arch-inspect [focus], the current session runs the audit without spawning subagents.

Live testing protocol for Rust projects: sync, discover project structure, execute binary end-to-end, detect anomalies, track coverage, file bug issues. Used by the rust-live-tester agent.